A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 00:45 UTC
[Build] update requirements of no-device for plugin usage (#12630)
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
Sophie du Couédic committed
Feb 4, 2025 at 14:19 UTC
649550f27e4ad35e7e3352800438991fdaf150a4
1 file changed
+1
-1
setup.py
+1
-1
@@ -556,7 +556,7 @@ def get_requirements() -> List[str]:
556
return resolved_requirements
557
558
if _no_device():
559
- requirements = _read_requirements("requirements-cpu.txt")
559
+ requirements = _read_requirements("requirements-common.txt")
560
elif _is_cuda():
561
requirements = _read_requirements("requirements-cuda.txt")
562
cuda_major, cuda_minor = torch.version.cuda.split(".")